Hugging Face's logo

vuiseng9
/
bert-base-squadv1

Question Answering
Transformers
PyTorch
ONNX
bert
Model card Files
xet
Community
1
bert-base-squadv1 / linear_layer_sparsity_85M_params_0.00_sparsity.md
Chua, Vui Seng
Add collaterals
d96569c
preview code
|
raw
history blame contribute delete
9.84 kB
 | | layer_id | layer_type | param_type | shape | nparam | nnz | sparsity |
|----:|:---------------------------------------------|:-------------|:-------------|:------------|---------:|--------:|-----------:|
| 5 | bert.encoder.layer.0.attention.self.query | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 7 | bert.encoder.layer.0.attention.self.key | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 9 | bert.encoder.layer.0.attention.self.value | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 11 | bert.encoder.layer.0.attention.output.dense | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 15 | bert.encoder.layer.0.intermediate.dense | Linear | weight | [3072, 768] | 2359296 | 2359296 | 0 |
| 17 | bert.encoder.layer.0.output.dense | Linear | weight | [768, 3072] | 2359296 | 2359296 | 0 |
| 21 | bert.encoder.layer.1.attention.self.query | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 23 | bert.encoder.layer.1.attention.self.key | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 25 | bert.encoder.layer.1.attention.self.value | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 27 | bert.encoder.layer.1.attention.output.dense | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 31 | bert.encoder.layer.1.intermediate.dense | Linear | weight | [3072, 768] | 2359296 | 2359296 | 0 |
| 33 | bert.encoder.layer.1.output.dense | Linear | weight | [768, 3072] | 2359296 | 2359296 | 0 |
| 37 | bert.encoder.layer.2.attention.self.query | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 39 | bert.encoder.layer.2.attention.self.key | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 41 | bert.encoder.layer.2.attention.self.value | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 43 | bert.encoder.layer.2.attention.output.dense | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 47 | bert.encoder.layer.2.intermediate.dense | Linear | weight | [3072, 768] | 2359296 | 2359296 | 0 |
| 49 | bert.encoder.layer.2.output.dense | Linear | weight | [768, 3072] | 2359296 | 2359296 | 0 |
| 53 | bert.encoder.layer.3.attention.self.query | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 55 | bert.encoder.layer.3.attention.self.key | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 57 | bert.encoder.layer.3.attention.self.value | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 59 | bert.encoder.layer.3.attention.output.dense | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 63 | bert.encoder.layer.3.intermediate.dense | Linear | weight | [3072, 768] | 2359296 | 2359296 | 0 |
| 65 | bert.encoder.layer.3.output.dense | Linear | weight | [768, 3072] | 2359296 | 2359296 | 0 |
| 69 | bert.encoder.layer.4.attention.self.query | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 71 | bert.encoder.layer.4.attention.self.key | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 73 | bert.encoder.layer.4.attention.self.value | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 75 | bert.encoder.layer.4.attention.output.dense | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 79 | bert.encoder.layer.4.intermediate.dense | Linear | weight | [3072, 768] | 2359296 | 2359296 | 0 |
| 81 | bert.encoder.layer.4.output.dense | Linear | weight | [768, 3072] | 2359296 | 2359296 | 0 |
| 85 | bert.encoder.layer.5.attention.self.query | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 87 | bert.encoder.layer.5.attention.self.key | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 89 | bert.encoder.layer.5.attention.self.value | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 91 | bert.encoder.layer.5.attention.output.dense | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 95 | bert.encoder.layer.5.intermediate.dense | Linear | weight | [3072, 768] | 2359296 | 2359296 | 0 |
| 97 | bert.encoder.layer.5.output.dense | Linear | weight | [768, 3072] | 2359296 | 2359296 | 0 |
| 101 | bert.encoder.layer.6.attention.self.query | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 103 | bert.encoder.layer.6.attention.self.key | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 105 | bert.encoder.layer.6.attention.self.value | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 107 | bert.encoder.layer.6.attention.output.dense | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 111 | bert.encoder.layer.6.intermediate.dense | Linear | weight | [3072, 768] | 2359296 | 2359296 | 0 |
| 113 | bert.encoder.layer.6.output.dense | Linear | weight | [768, 3072] | 2359296 | 2359296 | 0 |
| 117 | bert.encoder.layer.7.attention.self.query | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 119 | bert.encoder.layer.7.attention.self.key | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 121 | bert.encoder.layer.7.attention.self.value | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 123 | bert.encoder.layer.7.attention.output.dense | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 127 | bert.encoder.layer.7.intermediate.dense | Linear | weight | [3072, 768] | 2359296 | 2359296 | 0 |
| 129 | bert.encoder.layer.7.output.dense | Linear | weight | [768, 3072] | 2359296 | 2359296 | 0 |
| 133 | bert.encoder.layer.8.attention.self.query | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 135 | bert.encoder.layer.8.attention.self.key | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 137 | bert.encoder.layer.8.attention.self.value | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 139 | bert.encoder.layer.8.attention.output.dense | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 143 | bert.encoder.layer.8.intermediate.dense | Linear | weight | [3072, 768] | 2359296 | 2359296 | 0 |
| 145 | bert.encoder.layer.8.output.dense | Linear | weight | [768, 3072] | 2359296 | 2359296 | 0 |
| 149 | bert.encoder.layer.9.attention.self.query | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 151 | bert.encoder.layer.9.attention.self.key | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 153 | bert.encoder.layer.9.attention.self.value | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 155 | bert.encoder.layer.9.attention.output.dense | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 159 | bert.encoder.layer.9.intermediate.dense | Linear | weight | [3072, 768] | 2359296 | 2359296 | 0 |
| 161 | bert.encoder.layer.9.output.dense | Linear | weight | [768, 3072] | 2359296 | 2359296 | 0 |
| 165 | bert.encoder.layer.10.attention.self.query | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 167 | bert.encoder.layer.10.attention.self.key | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 169 | bert.encoder.layer.10.attention.self.value | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 171 | bert.encoder.layer.10.attention.output.dense | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 175 | bert.encoder.layer.10.intermediate.dense | Linear | weight | [3072, 768] | 2359296 | 2359296 | 0 |
| 177 | bert.encoder.layer.10.output.dense | Linear | weight | [768, 3072] | 2359296 | 2359296 | 0 |
| 181 | bert.encoder.layer.11.attention.self.query | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 183 | bert.encoder.layer.11.attention.self.key | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 185 | bert.encoder.layer.11.attention.self.value | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 187 | bert.encoder.layer.11.attention.output.dense | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
| 191 | bert.encoder.layer.11.intermediate.dense | Linear | weight | [3072, 768] | 2359296 | 2359296 | 0 |
| 193 | bert.encoder.layer.11.output.dense | Linear | weight | [768, 3072] | 2359296 | 2359296 | 0 |